root
commited on
Commit
•
9d18855
1
Parent(s):
da30210
updated by abhijithneilabraham
Browse files- config.json +56 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1156 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/pegasus-pubmed",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": true,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"PegasusForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.0,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 16,
|
| 19 |
+
"decoder_start_token_id": 0,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"encoder_attention_heads": 16,
|
| 22 |
+
"encoder_ffn_dim": 4096,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 16,
|
| 25 |
+
"eos_token_id": 1,
|
| 26 |
+
"extra_pos_embeddings": 1,
|
| 27 |
+
"forced_eos_token_id": 1,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "LABEL_0",
|
| 30 |
+
"1": "LABEL_1",
|
| 31 |
+
"2": "LABEL_2"
|
| 32 |
+
},
|
| 33 |
+
"init_std": 0.02,
|
| 34 |
+
"is_encoder_decoder": true,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_2": 2
|
| 39 |
+
},
|
| 40 |
+
"length_penalty": 0.8,
|
| 41 |
+
"max_length": 256,
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"min_length": 32,
|
| 44 |
+
"model_type": "pegasus",
|
| 45 |
+
"normalize_before": true,
|
| 46 |
+
"normalize_embedding": false,
|
| 47 |
+
"num_beams": 8,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"pad_token_id": 0,
|
| 50 |
+
"scale_embedding": true,
|
| 51 |
+
"static_position_embeddings": true,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.13.0",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 96103
|
| 56 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f1319e5dd880c5a18b9d501f2fa5479532848a6371931b492d44c9462f612ee
|
| 3 |
+
size 4550014615
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:244454df3d37b755ec0ce4d818b77e00986be8b506f9afffacdc6fa4f73d6135
|
| 3 |
+
size 2283834829
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acfc7c5d62e915d3c3b520f2600ffa7c59ec9807db73534c68cce067d1520ea9
|
| 3 |
+
size 17672
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ae62c7a2018fef5496da63a2bce6219d8ee040ceb325bad8ac1e7a13b7234df
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask_2>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"]}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
|
| 3 |
+
size 1912529
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"pad_token": "<pad>", "eos_token": "</s>", "unk_token": "<unk>", "mask_token": "<mask_2>", "mask_token_sent": "<mask_1>", "offset": 103, "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"], "model_max_length": 1024, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "google/pegasus-pubmed", "sp_model_kwargs": {}, "tokenizer_class": "PegasusTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.4883581399917603,
|
| 3 |
+
"best_model_checkpoint": "ccdv_pegasus_xsum_summarization/checkpoint-13500",
|
| 4 |
+
"epoch": 2.0012007204322595,
|
| 5 |
+
"global_step": 30000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.944411091099104e-05,
|
| 13 |
+
"loss": 1.3482,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"eval_gen_len": 190.7041,
|
| 19 |
+
"eval_loss": 1.5671061277389526,
|
| 20 |
+
"eval_rouge1": 43.9725,
|
| 21 |
+
"eval_rouge2": 20.8852,
|
| 22 |
+
"eval_rougeL": 29.6036,
|
| 23 |
+
"eval_rougeLsum": 39.2595,
|
| 24 |
+
"eval_runtime": 10745.9844,
|
| 25 |
+
"eval_samples_per_second": 0.617,
|
| 26 |
+
"eval_steps_per_second": 0.077,
|
| 27 |
+
"step": 500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 4.8888221821982085e-05,
|
| 32 |
+
"loss": 1.0335,
|
| 33 |
+
"step": 1000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"eval_gen_len": 159.8545,
|
| 38 |
+
"eval_loss": 1.5465657711029053,
|
| 39 |
+
"eval_rouge1": 44.9236,
|
| 40 |
+
"eval_rouge2": 21.1853,
|
| 41 |
+
"eval_rougeL": 30.4447,
|
| 42 |
+
"eval_rougeLsum": 39.9918,
|
| 43 |
+
"eval_runtime": 10231.1208,
|
| 44 |
+
"eval_samples_per_second": 0.648,
|
| 45 |
+
"eval_steps_per_second": 0.081,
|
| 46 |
+
"step": 1000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.1,
|
| 50 |
+
"learning_rate": 4.8332332732973116e-05,
|
| 51 |
+
"loss": 1.0184,
|
| 52 |
+
"step": 1500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1,
|
| 56 |
+
"eval_gen_len": 143.5453,
|
| 57 |
+
"eval_loss": 1.5334348678588867,
|
| 58 |
+
"eval_rouge1": 44.9483,
|
| 59 |
+
"eval_rouge2": 20.9962,
|
| 60 |
+
"eval_rougeL": 30.5328,
|
| 61 |
+
"eval_rougeLsum": 40.0531,
|
| 62 |
+
"eval_runtime": 8769.3615,
|
| 63 |
+
"eval_samples_per_second": 0.756,
|
| 64 |
+
"eval_steps_per_second": 0.095,
|
| 65 |
+
"step": 1500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13,
|
| 69 |
+
"learning_rate": 4.777644364396416e-05,
|
| 70 |
+
"loss": 1.0015,
|
| 71 |
+
"step": 2000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.13,
|
| 75 |
+
"eval_gen_len": 137.856,
|
| 76 |
+
"eval_loss": 1.529853343963623,
|
| 77 |
+
"eval_rouge1": 45.9034,
|
| 78 |
+
"eval_rouge2": 21.784,
|
| 79 |
+
"eval_rougeL": 31.4025,
|
| 80 |
+
"eval_rougeLsum": 40.8983,
|
| 81 |
+
"eval_runtime": 7582.4229,
|
| 82 |
+
"eval_samples_per_second": 0.875,
|
| 83 |
+
"eval_steps_per_second": 0.109,
|
| 84 |
+
"step": 2000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.17,
|
| 88 |
+
"learning_rate": 4.72205545549552e-05,
|
| 89 |
+
"loss": 1.0101,
|
| 90 |
+
"step": 2500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.17,
|
| 94 |
+
"eval_gen_len": 134.5485,
|
| 95 |
+
"eval_loss": 1.5291049480438232,
|
| 96 |
+
"eval_rouge1": 45.6738,
|
| 97 |
+
"eval_rouge2": 21.5853,
|
| 98 |
+
"eval_rougeL": 31.1439,
|
| 99 |
+
"eval_rougeLsum": 40.7442,
|
| 100 |
+
"eval_runtime": 6945.0608,
|
| 101 |
+
"eval_samples_per_second": 0.955,
|
| 102 |
+
"eval_steps_per_second": 0.12,
|
| 103 |
+
"step": 2500
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.2,
|
| 107 |
+
"learning_rate": 4.6664665465946236e-05,
|
| 108 |
+
"loss": 0.9973,
|
| 109 |
+
"step": 3000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2,
|
| 113 |
+
"eval_gen_len": 131.2587,
|
| 114 |
+
"eval_loss": 1.523977518081665,
|
| 115 |
+
"eval_rouge1": 45.5052,
|
| 116 |
+
"eval_rouge2": 21.4202,
|
| 117 |
+
"eval_rougeL": 31.1499,
|
| 118 |
+
"eval_rougeLsum": 40.5736,
|
| 119 |
+
"eval_runtime": 6458.4712,
|
| 120 |
+
"eval_samples_per_second": 1.027,
|
| 121 |
+
"eval_steps_per_second": 0.129,
|
| 122 |
+
"step": 3000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.23,
|
| 126 |
+
"learning_rate": 4.6108776376937274e-05,
|
| 127 |
+
"loss": 0.9855,
|
| 128 |
+
"step": 3500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.23,
|
| 132 |
+
"eval_gen_len": 131.0582,
|
| 133 |
+
"eval_loss": 1.5234577655792236,
|
| 134 |
+
"eval_rouge1": 45.8336,
|
| 135 |
+
"eval_rouge2": 21.7072,
|
| 136 |
+
"eval_rougeL": 31.439,
|
| 137 |
+
"eval_rougeLsum": 40.9387,
|
| 138 |
+
"eval_runtime": 6345.3859,
|
| 139 |
+
"eval_samples_per_second": 1.045,
|
| 140 |
+
"eval_steps_per_second": 0.131,
|
| 141 |
+
"step": 3500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.27,
|
| 145 |
+
"learning_rate": 4.555288728792831e-05,
|
| 146 |
+
"loss": 0.9868,
|
| 147 |
+
"step": 4000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.27,
|
| 151 |
+
"eval_gen_len": 127.9753,
|
| 152 |
+
"eval_loss": 1.5183237791061401,
|
| 153 |
+
"eval_rouge1": 45.6348,
|
| 154 |
+
"eval_rouge2": 21.5462,
|
| 155 |
+
"eval_rougeL": 31.3009,
|
| 156 |
+
"eval_rougeLsum": 40.6469,
|
| 157 |
+
"eval_runtime": 6091.2782,
|
| 158 |
+
"eval_samples_per_second": 1.089,
|
| 159 |
+
"eval_steps_per_second": 0.136,
|
| 160 |
+
"step": 4000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.3,
|
| 164 |
+
"learning_rate": 4.4996998198919356e-05,
|
| 165 |
+
"loss": 0.9802,
|
| 166 |
+
"step": 4500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.3,
|
| 170 |
+
"eval_gen_len": 127.78,
|
| 171 |
+
"eval_loss": 1.5132805109024048,
|
| 172 |
+
"eval_rouge1": 45.4357,
|
| 173 |
+
"eval_rouge2": 21.3339,
|
| 174 |
+
"eval_rougeL": 31.1304,
|
| 175 |
+
"eval_rougeLsum": 40.531,
|
| 176 |
+
"eval_runtime": 5970.8563,
|
| 177 |
+
"eval_samples_per_second": 1.111,
|
| 178 |
+
"eval_steps_per_second": 0.139,
|
| 179 |
+
"step": 4500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.33,
|
| 183 |
+
"learning_rate": 4.4441109109910394e-05,
|
| 184 |
+
"loss": 0.9743,
|
| 185 |
+
"step": 5000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.33,
|
| 189 |
+
"eval_gen_len": 126.9619,
|
| 190 |
+
"eval_loss": 1.5101301670074463,
|
| 191 |
+
"eval_rouge1": 45.4845,
|
| 192 |
+
"eval_rouge2": 21.4302,
|
| 193 |
+
"eval_rougeL": 31.2033,
|
| 194 |
+
"eval_rougeLsum": 40.5934,
|
| 195 |
+
"eval_runtime": 5820.9525,
|
| 196 |
+
"eval_samples_per_second": 1.14,
|
| 197 |
+
"eval_steps_per_second": 0.143,
|
| 198 |
+
"step": 5000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.37,
|
| 202 |
+
"learning_rate": 4.388522002090143e-05,
|
| 203 |
+
"loss": 0.972,
|
| 204 |
+
"step": 5500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.37,
|
| 208 |
+
"eval_gen_len": 127.1796,
|
| 209 |
+
"eval_loss": 1.5053614377975464,
|
| 210 |
+
"eval_rouge1": 45.196,
|
| 211 |
+
"eval_rouge2": 21.1882,
|
| 212 |
+
"eval_rougeL": 30.9407,
|
| 213 |
+
"eval_rougeLsum": 40.2648,
|
| 214 |
+
"eval_runtime": 5768.324,
|
| 215 |
+
"eval_samples_per_second": 1.15,
|
| 216 |
+
"eval_steps_per_second": 0.144,
|
| 217 |
+
"step": 5500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.4,
|
| 221 |
+
"learning_rate": 4.332933093189247e-05,
|
| 222 |
+
"loss": 0.9651,
|
| 223 |
+
"step": 6000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.4,
|
| 227 |
+
"eval_gen_len": 126.9254,
|
| 228 |
+
"eval_loss": 1.5030862092971802,
|
| 229 |
+
"eval_rouge1": 45.4822,
|
| 230 |
+
"eval_rouge2": 21.4363,
|
| 231 |
+
"eval_rougeL": 31.1422,
|
| 232 |
+
"eval_rougeLsum": 40.5397,
|
| 233 |
+
"eval_runtime": 5665.8916,
|
| 234 |
+
"eval_samples_per_second": 1.171,
|
| 235 |
+
"eval_steps_per_second": 0.146,
|
| 236 |
+
"step": 6000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.43,
|
| 240 |
+
"learning_rate": 4.277344184288351e-05,
|
| 241 |
+
"loss": 0.9758,
|
| 242 |
+
"step": 6500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.43,
|
| 246 |
+
"eval_gen_len": 126.4933,
|
| 247 |
+
"eval_loss": 1.495548963546753,
|
| 248 |
+
"eval_rouge1": 45.299,
|
| 249 |
+
"eval_rouge2": 21.346,
|
| 250 |
+
"eval_rougeL": 31.0361,
|
| 251 |
+
"eval_rougeLsum": 40.3325,
|
| 252 |
+
"eval_runtime": 5589.2093,
|
| 253 |
+
"eval_samples_per_second": 1.187,
|
| 254 |
+
"eval_steps_per_second": 0.149,
|
| 255 |
+
"step": 6500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.47,
|
| 259 |
+
"learning_rate": 4.221755275387455e-05,
|
| 260 |
+
"loss": 0.9652,
|
| 261 |
+
"step": 7000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.47,
|
| 265 |
+
"eval_gen_len": 126.0859,
|
| 266 |
+
"eval_loss": 1.4975615739822388,
|
| 267 |
+
"eval_rouge1": 45.4694,
|
| 268 |
+
"eval_rouge2": 21.5044,
|
| 269 |
+
"eval_rougeL": 31.1786,
|
| 270 |
+
"eval_rougeLsum": 40.5032,
|
| 271 |
+
"eval_runtime": 5569.8623,
|
| 272 |
+
"eval_samples_per_second": 1.191,
|
| 273 |
+
"eval_steps_per_second": 0.149,
|
| 274 |
+
"step": 7000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.5,
|
| 278 |
+
"learning_rate": 4.166166366486558e-05,
|
| 279 |
+
"loss": 0.9601,
|
| 280 |
+
"step": 7500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.5,
|
| 284 |
+
"eval_gen_len": 126.8815,
|
| 285 |
+
"eval_loss": 1.4945002794265747,
|
| 286 |
+
"eval_rouge1": 45.1971,
|
| 287 |
+
"eval_rouge2": 21.2682,
|
| 288 |
+
"eval_rougeL": 30.9321,
|
| 289 |
+
"eval_rougeLsum": 40.2959,
|
| 290 |
+
"eval_runtime": 5557.7856,
|
| 291 |
+
"eval_samples_per_second": 1.193,
|
| 292 |
+
"eval_steps_per_second": 0.149,
|
| 293 |
+
"step": 7500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.53,
|
| 297 |
+
"learning_rate": 4.110577457585663e-05,
|
| 298 |
+
"loss": 0.9502,
|
| 299 |
+
"step": 8000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.53,
|
| 303 |
+
"eval_gen_len": 126.4628,
|
| 304 |
+
"eval_loss": 1.49406898021698,
|
| 305 |
+
"eval_rouge1": 45.5653,
|
| 306 |
+
"eval_rouge2": 21.5655,
|
| 307 |
+
"eval_rougeL": 31.2703,
|
| 308 |
+
"eval_rougeLsum": 40.5622,
|
| 309 |
+
"eval_runtime": 5535.3927,
|
| 310 |
+
"eval_samples_per_second": 1.198,
|
| 311 |
+
"eval_steps_per_second": 0.15,
|
| 312 |
+
"step": 8000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.57,
|
| 316 |
+
"learning_rate": 4.0549885486847665e-05,
|
| 317 |
+
"loss": 0.9537,
|
| 318 |
+
"step": 8500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.57,
|
| 322 |
+
"eval_gen_len": 126.5709,
|
| 323 |
+
"eval_loss": 1.4941043853759766,
|
| 324 |
+
"eval_rouge1": 45.2806,
|
| 325 |
+
"eval_rouge2": 21.2587,
|
| 326 |
+
"eval_rougeL": 30.93,
|
| 327 |
+
"eval_rougeLsum": 40.354,
|
| 328 |
+
"eval_runtime": 5533.5879,
|
| 329 |
+
"eval_samples_per_second": 1.199,
|
| 330 |
+
"eval_steps_per_second": 0.15,
|
| 331 |
+
"step": 8500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6,
|
| 335 |
+
"learning_rate": 3.999399639783871e-05,
|
| 336 |
+
"loss": 0.9629,
|
| 337 |
+
"step": 9000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.6,
|
| 341 |
+
"eval_gen_len": 126.547,
|
| 342 |
+
"eval_loss": 1.4939745664596558,
|
| 343 |
+
"eval_rouge1": 45.2474,
|
| 344 |
+
"eval_rouge2": 21.275,
|
| 345 |
+
"eval_rougeL": 30.9302,
|
| 346 |
+
"eval_rougeLsum": 40.3377,
|
| 347 |
+
"eval_runtime": 5530.7272,
|
| 348 |
+
"eval_samples_per_second": 1.199,
|
| 349 |
+
"eval_steps_per_second": 0.15,
|
| 350 |
+
"step": 9000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.63,
|
| 354 |
+
"learning_rate": 3.943810730882974e-05,
|
| 355 |
+
"loss": 0.9528,
|
| 356 |
+
"step": 9500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.63,
|
| 360 |
+
"eval_gen_len": 126.768,
|
| 361 |
+
"eval_loss": 1.4947481155395508,
|
| 362 |
+
"eval_rouge1": 45.3619,
|
| 363 |
+
"eval_rouge2": 21.3754,
|
| 364 |
+
"eval_rougeL": 31.0723,
|
| 365 |
+
"eval_rougeLsum": 40.4162,
|
| 366 |
+
"eval_runtime": 5524.5717,
|
| 367 |
+
"eval_samples_per_second": 1.201,
|
| 368 |
+
"eval_steps_per_second": 0.15,
|
| 369 |
+
"step": 9500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.67,
|
| 373 |
+
"learning_rate": 3.888221821982078e-05,
|
| 374 |
+
"loss": 0.9532,
|
| 375 |
+
"step": 10000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.67,
|
| 379 |
+
"eval_gen_len": 126.5323,
|
| 380 |
+
"eval_loss": 1.4923893213272095,
|
| 381 |
+
"eval_rouge1": 45.5763,
|
| 382 |
+
"eval_rouge2": 21.6469,
|
| 383 |
+
"eval_rougeL": 31.2585,
|
| 384 |
+
"eval_rougeLsum": 40.5722,
|
| 385 |
+
"eval_runtime": 5518.2912,
|
| 386 |
+
"eval_samples_per_second": 1.202,
|
| 387 |
+
"eval_steps_per_second": 0.15,
|
| 388 |
+
"step": 10000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7,
|
| 392 |
+
"learning_rate": 3.832632913081182e-05,
|
| 393 |
+
"loss": 0.945,
|
| 394 |
+
"step": 10500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7,
|
| 398 |
+
"eval_gen_len": 126.69,
|
| 399 |
+
"eval_loss": 1.4898710250854492,
|
| 400 |
+
"eval_rouge1": 45.2629,
|
| 401 |
+
"eval_rouge2": 21.3471,
|
| 402 |
+
"eval_rougeL": 31.0405,
|
| 403 |
+
"eval_rougeLsum": 40.3211,
|
| 404 |
+
"eval_runtime": 6184.8714,
|
| 405 |
+
"eval_samples_per_second": 1.072,
|
| 406 |
+
"eval_steps_per_second": 0.134,
|
| 407 |
+
"step": 10500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.73,
|
| 411 |
+
"learning_rate": 3.777044004180286e-05,
|
| 412 |
+
"loss": 0.9464,
|
| 413 |
+
"step": 11000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.73,
|
| 417 |
+
"eval_gen_len": 126.9052,
|
| 418 |
+
"eval_loss": 1.489205002784729,
|
| 419 |
+
"eval_rouge1": 45.3769,
|
| 420 |
+
"eval_rouge2": 21.3457,
|
| 421 |
+
"eval_rougeL": 30.9968,
|
| 422 |
+
"eval_rougeLsum": 40.388,
|
| 423 |
+
"eval_runtime": 5520.5499,
|
| 424 |
+
"eval_samples_per_second": 1.202,
|
| 425 |
+
"eval_steps_per_second": 0.15,
|
| 426 |
+
"step": 11000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.77,
|
| 430 |
+
"learning_rate": 3.7214550952793906e-05,
|
| 431 |
+
"loss": 0.9544,
|
| 432 |
+
"step": 11500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.77,
|
| 436 |
+
"eval_gen_len": 126.5739,
|
| 437 |
+
"eval_loss": 1.4892535209655762,
|
| 438 |
+
"eval_rouge1": 45.411,
|
| 439 |
+
"eval_rouge2": 21.3852,
|
| 440 |
+
"eval_rougeL": 31.0295,
|
| 441 |
+
"eval_rougeLsum": 40.4881,
|
| 442 |
+
"eval_runtime": 5521.4271,
|
| 443 |
+
"eval_samples_per_second": 1.201,
|
| 444 |
+
"eval_steps_per_second": 0.15,
|
| 445 |
+
"step": 11500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.8,
|
| 449 |
+
"learning_rate": 3.6658661863784937e-05,
|
| 450 |
+
"loss": 0.9467,
|
| 451 |
+
"step": 12000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8,
|
| 455 |
+
"eval_gen_len": 126.7315,
|
| 456 |
+
"eval_loss": 1.4929231405258179,
|
| 457 |
+
"eval_rouge1": 45.4345,
|
| 458 |
+
"eval_rouge2": 21.4378,
|
| 459 |
+
"eval_rougeL": 31.1163,
|
| 460 |
+
"eval_rougeLsum": 40.4393,
|
| 461 |
+
"eval_runtime": 5524.2145,
|
| 462 |
+
"eval_samples_per_second": 1.201,
|
| 463 |
+
"eval_steps_per_second": 0.15,
|
| 464 |
+
"step": 12000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.83,
|
| 468 |
+
"learning_rate": 3.610277277477598e-05,
|
| 469 |
+
"loss": 0.9517,
|
| 470 |
+
"step": 12500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.83,
|
| 474 |
+
"eval_gen_len": 126.58,
|
| 475 |
+
"eval_loss": 1.4917516708374023,
|
| 476 |
+
"eval_rouge1": 45.3614,
|
| 477 |
+
"eval_rouge2": 21.3396,
|
| 478 |
+
"eval_rougeL": 30.9925,
|
| 479 |
+
"eval_rougeLsum": 40.3636,
|
| 480 |
+
"eval_runtime": 5514.201,
|
| 481 |
+
"eval_samples_per_second": 1.203,
|
| 482 |
+
"eval_steps_per_second": 0.151,
|
| 483 |
+
"step": 12500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.87,
|
| 487 |
+
"learning_rate": 3.554688368576702e-05,
|
| 488 |
+
"loss": 0.9497,
|
| 489 |
+
"step": 13000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.87,
|
| 493 |
+
"eval_gen_len": 126.7977,
|
| 494 |
+
"eval_loss": 1.4918133020401,
|
| 495 |
+
"eval_rouge1": 45.2485,
|
| 496 |
+
"eval_rouge2": 21.2367,
|
| 497 |
+
"eval_rougeL": 30.9282,
|
| 498 |
+
"eval_rougeLsum": 40.3438,
|
| 499 |
+
"eval_runtime": 6509.3818,
|
| 500 |
+
"eval_samples_per_second": 1.019,
|
| 501 |
+
"eval_steps_per_second": 0.128,
|
| 502 |
+
"step": 13000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.9,
|
| 506 |
+
"learning_rate": 3.499099459675806e-05,
|
| 507 |
+
"loss": 0.9386,
|
| 508 |
+
"step": 13500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.9,
|
| 512 |
+
"eval_gen_len": 126.7524,
|
| 513 |
+
"eval_loss": 1.4883581399917603,
|
| 514 |
+
"eval_rouge1": 45.5038,
|
| 515 |
+
"eval_rouge2": 21.5064,
|
| 516 |
+
"eval_rougeL": 31.2132,
|
| 517 |
+
"eval_rougeLsum": 40.5696,
|
| 518 |
+
"eval_runtime": 5529.57,
|
| 519 |
+
"eval_samples_per_second": 1.2,
|
| 520 |
+
"eval_steps_per_second": 0.15,
|
| 521 |
+
"step": 13500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.93,
|
| 525 |
+
"learning_rate": 3.4435105507749095e-05,
|
| 526 |
+
"loss": 0.9473,
|
| 527 |
+
"step": 14000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.93,
|
| 531 |
+
"eval_gen_len": 126.6534,
|
| 532 |
+
"eval_loss": 1.4918317794799805,
|
| 533 |
+
"eval_rouge1": 45.2367,
|
| 534 |
+
"eval_rouge2": 21.2615,
|
| 535 |
+
"eval_rougeL": 30.9179,
|
| 536 |
+
"eval_rougeLsum": 40.2548,
|
| 537 |
+
"eval_runtime": 5515.735,
|
| 538 |
+
"eval_samples_per_second": 1.203,
|
| 539 |
+
"eval_steps_per_second": 0.15,
|
| 540 |
+
"step": 14000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.97,
|
| 544 |
+
"learning_rate": 3.387921641874013e-05,
|
| 545 |
+
"loss": 0.9235,
|
| 546 |
+
"step": 14500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.97,
|
| 550 |
+
"eval_gen_len": 126.5972,
|
| 551 |
+
"eval_loss": 1.4897193908691406,
|
| 552 |
+
"eval_rouge1": 45.8027,
|
| 553 |
+
"eval_rouge2": 21.7228,
|
| 554 |
+
"eval_rougeL": 31.3946,
|
| 555 |
+
"eval_rougeLsum": 40.764,
|
| 556 |
+
"eval_runtime": 5518.2889,
|
| 557 |
+
"eval_samples_per_second": 1.202,
|
| 558 |
+
"eval_steps_per_second": 0.15,
|
| 559 |
+
"step": 14500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.0,
|
| 563 |
+
"learning_rate": 3.332332732973118e-05,
|
| 564 |
+
"loss": 0.9344,
|
| 565 |
+
"step": 15000
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.0,
|
| 569 |
+
"eval_gen_len": 126.9212,
|
| 570 |
+
"eval_loss": 1.4973394870758057,
|
| 571 |
+
"eval_rouge1": 44.8773,
|
| 572 |
+
"eval_rouge2": 20.9475,
|
| 573 |
+
"eval_rougeL": 30.5827,
|
| 574 |
+
"eval_rougeLsum": 39.9489,
|
| 575 |
+
"eval_runtime": 5510.2549,
|
| 576 |
+
"eval_samples_per_second": 1.204,
|
| 577 |
+
"eval_steps_per_second": 0.151,
|
| 578 |
+
"step": 15000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.03,
|
| 582 |
+
"learning_rate": 3.2767438240722215e-05,
|
| 583 |
+
"loss": 0.9139,
|
| 584 |
+
"step": 15500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.03,
|
| 588 |
+
"eval_gen_len": 126.692,
|
| 589 |
+
"eval_loss": 1.5064738988876343,
|
| 590 |
+
"eval_rouge1": 45.4207,
|
| 591 |
+
"eval_rouge2": 21.3856,
|
| 592 |
+
"eval_rougeL": 31.0837,
|
| 593 |
+
"eval_rougeLsum": 40.4414,
|
| 594 |
+
"eval_runtime": 5526.017,
|
| 595 |
+
"eval_samples_per_second": 1.2,
|
| 596 |
+
"eval_steps_per_second": 0.15,
|
| 597 |
+
"step": 15500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.07,
|
| 601 |
+
"learning_rate": 3.221154915171325e-05,
|
| 602 |
+
"loss": 0.8939,
|
| 603 |
+
"step": 16000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.07,
|
| 607 |
+
"eval_gen_len": 126.5179,
|
| 608 |
+
"eval_loss": 1.508902668952942,
|
| 609 |
+
"eval_rouge1": 45.5575,
|
| 610 |
+
"eval_rouge2": 21.5153,
|
| 611 |
+
"eval_rougeL": 31.2115,
|
| 612 |
+
"eval_rougeLsum": 40.5517,
|
| 613 |
+
"eval_runtime": 5698.8075,
|
| 614 |
+
"eval_samples_per_second": 1.164,
|
| 615 |
+
"eval_steps_per_second": 0.146,
|
| 616 |
+
"step": 16000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.1,
|
| 620 |
+
"learning_rate": 3.165566006270429e-05,
|
| 621 |
+
"loss": 0.8968,
|
| 622 |
+
"step": 16500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.1,
|
| 626 |
+
"eval_gen_len": 126.5447,
|
| 627 |
+
"eval_loss": 1.5106098651885986,
|
| 628 |
+
"eval_rouge1": 45.4574,
|
| 629 |
+
"eval_rouge2": 21.4786,
|
| 630 |
+
"eval_rougeL": 31.1065,
|
| 631 |
+
"eval_rougeLsum": 40.495,
|
| 632 |
+
"eval_runtime": 5606.9538,
|
| 633 |
+
"eval_samples_per_second": 1.183,
|
| 634 |
+
"eval_steps_per_second": 0.148,
|
| 635 |
+
"step": 16500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.13,
|
| 639 |
+
"learning_rate": 3.109977097369533e-05,
|
| 640 |
+
"loss": 0.8999,
|
| 641 |
+
"step": 17000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.13,
|
| 645 |
+
"eval_gen_len": 126.6894,
|
| 646 |
+
"eval_loss": 1.5100876092910767,
|
| 647 |
+
"eval_rouge1": 45.4805,
|
| 648 |
+
"eval_rouge2": 21.4579,
|
| 649 |
+
"eval_rougeL": 31.1062,
|
| 650 |
+
"eval_rougeLsum": 40.5138,
|
| 651 |
+
"eval_runtime": 5594.355,
|
| 652 |
+
"eval_samples_per_second": 1.186,
|
| 653 |
+
"eval_steps_per_second": 0.148,
|
| 654 |
+
"step": 17000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.17,
|
| 658 |
+
"learning_rate": 3.054388188468637e-05,
|
| 659 |
+
"loss": 0.903,
|
| 660 |
+
"step": 17500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.17,
|
| 664 |
+
"eval_gen_len": 126.5988,
|
| 665 |
+
"eval_loss": 1.5103389024734497,
|
| 666 |
+
"eval_rouge1": 45.495,
|
| 667 |
+
"eval_rouge2": 21.4395,
|
| 668 |
+
"eval_rougeL": 31.1445,
|
| 669 |
+
"eval_rougeLsum": 40.4949,
|
| 670 |
+
"eval_runtime": 5586.6059,
|
| 671 |
+
"eval_samples_per_second": 1.187,
|
| 672 |
+
"eval_steps_per_second": 0.149,
|
| 673 |
+
"step": 17500
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.2,
|
| 677 |
+
"learning_rate": 2.9987992795677407e-05,
|
| 678 |
+
"loss": 0.8988,
|
| 679 |
+
"step": 18000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.2,
|
| 683 |
+
"eval_gen_len": 126.5643,
|
| 684 |
+
"eval_loss": 1.5120760202407837,
|
| 685 |
+
"eval_rouge1": 45.2764,
|
| 686 |
+
"eval_rouge2": 21.2652,
|
| 687 |
+
"eval_rougeL": 30.944,
|
| 688 |
+
"eval_rougeLsum": 40.3249,
|
| 689 |
+
"eval_runtime": 5558.8098,
|
| 690 |
+
"eval_samples_per_second": 1.193,
|
| 691 |
+
"eval_steps_per_second": 0.149,
|
| 692 |
+
"step": 18000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.23,
|
| 696 |
+
"learning_rate": 2.9432103706668445e-05,
|
| 697 |
+
"loss": 0.9027,
|
| 698 |
+
"step": 18500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.23,
|
| 702 |
+
"eval_gen_len": 126.8441,
|
| 703 |
+
"eval_loss": 1.5092076063156128,
|
| 704 |
+
"eval_rouge1": 45.4884,
|
| 705 |
+
"eval_rouge2": 21.4334,
|
| 706 |
+
"eval_rougeL": 31.0499,
|
| 707 |
+
"eval_rougeLsum": 40.4796,
|
| 708 |
+
"eval_runtime": 5536.9856,
|
| 709 |
+
"eval_samples_per_second": 1.198,
|
| 710 |
+
"eval_steps_per_second": 0.15,
|
| 711 |
+
"step": 18500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.27,
|
| 715 |
+
"learning_rate": 2.8876214617659486e-05,
|
| 716 |
+
"loss": 0.9044,
|
| 717 |
+
"step": 19000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.27,
|
| 721 |
+
"eval_gen_len": 126.8737,
|
| 722 |
+
"eval_loss": 1.5079020261764526,
|
| 723 |
+
"eval_rouge1": 45.5708,
|
| 724 |
+
"eval_rouge2": 21.5358,
|
| 725 |
+
"eval_rougeL": 31.1862,
|
| 726 |
+
"eval_rougeLsum": 40.594,
|
| 727 |
+
"eval_runtime": 5524.867,
|
| 728 |
+
"eval_samples_per_second": 1.201,
|
| 729 |
+
"eval_steps_per_second": 0.15,
|
| 730 |
+
"step": 19000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.3,
|
| 734 |
+
"learning_rate": 2.8320325528650527e-05,
|
| 735 |
+
"loss": 0.906,
|
| 736 |
+
"step": 19500
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.3,
|
| 740 |
+
"eval_gen_len": 126.8627,
|
| 741 |
+
"eval_loss": 1.5116254091262817,
|
| 742 |
+
"eval_rouge1": 45.4542,
|
| 743 |
+
"eval_rouge2": 21.4172,
|
| 744 |
+
"eval_rougeL": 31.0754,
|
| 745 |
+
"eval_rougeLsum": 40.439,
|
| 746 |
+
"eval_runtime": 5524.341,
|
| 747 |
+
"eval_samples_per_second": 1.201,
|
| 748 |
+
"eval_steps_per_second": 0.15,
|
| 749 |
+
"step": 19500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.33,
|
| 753 |
+
"learning_rate": 2.776443643964157e-05,
|
| 754 |
+
"loss": 0.8994,
|
| 755 |
+
"step": 20000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.33,
|
| 759 |
+
"eval_gen_len": 126.8206,
|
| 760 |
+
"eval_loss": 1.5085355043411255,
|
| 761 |
+
"eval_rouge1": 45.5424,
|
| 762 |
+
"eval_rouge2": 21.5009,
|
| 763 |
+
"eval_rougeL": 31.1428,
|
| 764 |
+
"eval_rougeLsum": 40.5667,
|
| 765 |
+
"eval_runtime": 5528.1375,
|
| 766 |
+
"eval_samples_per_second": 1.2,
|
| 767 |
+
"eval_steps_per_second": 0.15,
|
| 768 |
+
"step": 20000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.37,
|
| 772 |
+
"learning_rate": 2.7208547350632603e-05,
|
| 773 |
+
"loss": 0.9088,
|
| 774 |
+
"step": 20500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.37,
|
| 778 |
+
"eval_gen_len": 126.7414,
|
| 779 |
+
"eval_loss": 1.5124515295028687,
|
| 780 |
+
"eval_rouge1": 45.3129,
|
| 781 |
+
"eval_rouge2": 21.2629,
|
| 782 |
+
"eval_rougeL": 30.9461,
|
| 783 |
+
"eval_rougeLsum": 40.3271,
|
| 784 |
+
"eval_runtime": 5534.3419,
|
| 785 |
+
"eval_samples_per_second": 1.199,
|
| 786 |
+
"eval_steps_per_second": 0.15,
|
| 787 |
+
"step": 20500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.4,
|
| 791 |
+
"learning_rate": 2.665265826162364e-05,
|
| 792 |
+
"loss": 0.8983,
|
| 793 |
+
"step": 21000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.4,
|
| 797 |
+
"eval_gen_len": 126.357,
|
| 798 |
+
"eval_loss": 1.5135449171066284,
|
| 799 |
+
"eval_rouge1": 45.6846,
|
| 800 |
+
"eval_rouge2": 21.6282,
|
| 801 |
+
"eval_rougeL": 31.2929,
|
| 802 |
+
"eval_rougeLsum": 40.6821,
|
| 803 |
+
"eval_runtime": 5538.2932,
|
| 804 |
+
"eval_samples_per_second": 1.198,
|
| 805 |
+
"eval_steps_per_second": 0.15,
|
| 806 |
+
"step": 21000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.43,
|
| 810 |
+
"learning_rate": 2.6096769172614682e-05,
|
| 811 |
+
"loss": 0.907,
|
| 812 |
+
"step": 21500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.43,
|
| 816 |
+
"eval_gen_len": 127.0029,
|
| 817 |
+
"eval_loss": 1.5076923370361328,
|
| 818 |
+
"eval_rouge1": 45.4873,
|
| 819 |
+
"eval_rouge2": 21.455,
|
| 820 |
+
"eval_rougeL": 31.1193,
|
| 821 |
+
"eval_rougeLsum": 40.5128,
|
| 822 |
+
"eval_runtime": 5539.9922,
|
| 823 |
+
"eval_samples_per_second": 1.197,
|
| 824 |
+
"eval_steps_per_second": 0.15,
|
| 825 |
+
"step": 21500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.47,
|
| 829 |
+
"learning_rate": 2.5540880083605723e-05,
|
| 830 |
+
"loss": 0.9097,
|
| 831 |
+
"step": 22000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.47,
|
| 835 |
+
"eval_gen_len": 126.8553,
|
| 836 |
+
"eval_loss": 1.5052434206008911,
|
| 837 |
+
"eval_rouge1": 45.5988,
|
| 838 |
+
"eval_rouge2": 21.6134,
|
| 839 |
+
"eval_rougeL": 31.247,
|
| 840 |
+
"eval_rougeLsum": 40.58,
|
| 841 |
+
"eval_runtime": 5539.7468,
|
| 842 |
+
"eval_samples_per_second": 1.197,
|
| 843 |
+
"eval_steps_per_second": 0.15,
|
| 844 |
+
"step": 22000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.5,
|
| 848 |
+
"learning_rate": 2.498499099459676e-05,
|
| 849 |
+
"loss": 0.9033,
|
| 850 |
+
"step": 22500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5,
|
| 854 |
+
"eval_gen_len": 127.0048,
|
| 855 |
+
"eval_loss": 1.5133850574493408,
|
| 856 |
+
"eval_rouge1": 45.3223,
|
| 857 |
+
"eval_rouge2": 21.2968,
|
| 858 |
+
"eval_rougeL": 30.9357,
|
| 859 |
+
"eval_rougeLsum": 40.3813,
|
| 860 |
+
"eval_runtime": 9404.5,
|
| 861 |
+
"eval_samples_per_second": 0.705,
|
| 862 |
+
"eval_steps_per_second": 0.088,
|
| 863 |
+
"step": 22500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.53,
|
| 867 |
+
"learning_rate": 2.44291019055878e-05,
|
| 868 |
+
"loss": 0.8925,
|
| 869 |
+
"step": 23000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.53,
|
| 873 |
+
"eval_gen_len": 126.7316,
|
| 874 |
+
"eval_loss": 1.510839819908142,
|
| 875 |
+
"eval_rouge1": 45.6747,
|
| 876 |
+
"eval_rouge2": 21.6374,
|
| 877 |
+
"eval_rougeL": 31.31,
|
| 878 |
+
"eval_rougeLsum": 40.7015,
|
| 879 |
+
"eval_runtime": 22732.2519,
|
| 880 |
+
"eval_samples_per_second": 0.292,
|
| 881 |
+
"eval_steps_per_second": 0.037,
|
| 882 |
+
"step": 23000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.57,
|
| 886 |
+
"learning_rate": 2.387321281657884e-05,
|
| 887 |
+
"loss": 0.8913,
|
| 888 |
+
"step": 23500
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.57,
|
| 892 |
+
"eval_gen_len": 126.6869,
|
| 893 |
+
"eval_loss": 1.5129714012145996,
|
| 894 |
+
"eval_rouge1": 45.6531,
|
| 895 |
+
"eval_rouge2": 21.6354,
|
| 896 |
+
"eval_rougeL": 31.2956,
|
| 897 |
+
"eval_rougeLsum": 40.6555,
|
| 898 |
+
"eval_runtime": 6945.8776,
|
| 899 |
+
"eval_samples_per_second": 0.955,
|
| 900 |
+
"eval_steps_per_second": 0.119,
|
| 901 |
+
"step": 23500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.6,
|
| 905 |
+
"learning_rate": 2.3317323727569874e-05,
|
| 906 |
+
"loss": 0.8931,
|
| 907 |
+
"step": 24000
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.6,
|
| 911 |
+
"eval_gen_len": 126.4862,
|
| 912 |
+
"eval_loss": 1.5111068487167358,
|
| 913 |
+
"eval_rouge1": 45.7876,
|
| 914 |
+
"eval_rouge2": 21.7115,
|
| 915 |
+
"eval_rougeL": 31.3274,
|
| 916 |
+
"eval_rougeLsum": 40.7579,
|
| 917 |
+
"eval_runtime": 5539.5619,
|
| 918 |
+
"eval_samples_per_second": 1.197,
|
| 919 |
+
"eval_steps_per_second": 0.15,
|
| 920 |
+
"step": 24000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.63,
|
| 924 |
+
"learning_rate": 2.2761434638560915e-05,
|
| 925 |
+
"loss": 0.9009,
|
| 926 |
+
"step": 24500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.63,
|
| 930 |
+
"eval_gen_len": 126.6229,
|
| 931 |
+
"eval_loss": 1.5083845853805542,
|
| 932 |
+
"eval_rouge1": 45.6359,
|
| 933 |
+
"eval_rouge2": 21.583,
|
| 934 |
+
"eval_rougeL": 31.2775,
|
| 935 |
+
"eval_rougeLsum": 40.6351,
|
| 936 |
+
"eval_runtime": 5545.0209,
|
| 937 |
+
"eval_samples_per_second": 1.196,
|
| 938 |
+
"eval_steps_per_second": 0.15,
|
| 939 |
+
"step": 24500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.67,
|
| 943 |
+
"learning_rate": 2.2205545549551953e-05,
|
| 944 |
+
"loss": 0.8925,
|
| 945 |
+
"step": 25000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.67,
|
| 949 |
+
"eval_gen_len": 126.8396,
|
| 950 |
+
"eval_loss": 1.5094473361968994,
|
| 951 |
+
"eval_rouge1": 45.397,
|
| 952 |
+
"eval_rouge2": 21.4266,
|
| 953 |
+
"eval_rougeL": 31.082,
|
| 954 |
+
"eval_rougeLsum": 40.4261,
|
| 955 |
+
"eval_runtime": 5534.6802,
|
| 956 |
+
"eval_samples_per_second": 1.198,
|
| 957 |
+
"eval_steps_per_second": 0.15,
|
| 958 |
+
"step": 25000
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.7,
|
| 962 |
+
"learning_rate": 2.1649656460542994e-05,
|
| 963 |
+
"loss": 0.8991,
|
| 964 |
+
"step": 25500
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.7,
|
| 968 |
+
"eval_gen_len": 126.722,
|
| 969 |
+
"eval_loss": 1.512014627456665,
|
| 970 |
+
"eval_rouge1": 45.2851,
|
| 971 |
+
"eval_rouge2": 21.2798,
|
| 972 |
+
"eval_rougeL": 30.8973,
|
| 973 |
+
"eval_rougeLsum": 40.2787,
|
| 974 |
+
"eval_runtime": 5538.1327,
|
| 975 |
+
"eval_samples_per_second": 1.198,
|
| 976 |
+
"eval_steps_per_second": 0.15,
|
| 977 |
+
"step": 25500
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.73,
|
| 981 |
+
"learning_rate": 2.1093767371534032e-05,
|
| 982 |
+
"loss": 0.9019,
|
| 983 |
+
"step": 26000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.73,
|
| 987 |
+
"eval_gen_len": 126.8048,
|
| 988 |
+
"eval_loss": 1.510252833366394,
|
| 989 |
+
"eval_rouge1": 45.2905,
|
| 990 |
+
"eval_rouge2": 21.2992,
|
| 991 |
+
"eval_rougeL": 30.9204,
|
| 992 |
+
"eval_rougeLsum": 40.3262,
|
| 993 |
+
"eval_runtime": 5535.5354,
|
| 994 |
+
"eval_samples_per_second": 1.198,
|
| 995 |
+
"eval_steps_per_second": 0.15,
|
| 996 |
+
"step": 26000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.77,
|
| 1000 |
+
"learning_rate": 2.0537878282525073e-05,
|
| 1001 |
+
"loss": 0.891,
|
| 1002 |
+
"step": 26500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.77,
|
| 1006 |
+
"eval_gen_len": 126.2902,
|
| 1007 |
+
"eval_loss": 1.5112383365631104,
|
| 1008 |
+
"eval_rouge1": 45.7091,
|
| 1009 |
+
"eval_rouge2": 21.6159,
|
| 1010 |
+
"eval_rougeL": 31.2889,
|
| 1011 |
+
"eval_rougeLsum": 40.6986,
|
| 1012 |
+
"eval_runtime": 5537.5343,
|
| 1013 |
+
"eval_samples_per_second": 1.198,
|
| 1014 |
+
"eval_steps_per_second": 0.15,
|
| 1015 |
+
"step": 26500
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.8,
|
| 1019 |
+
"learning_rate": 1.998198919351611e-05,
|
| 1020 |
+
"loss": 0.898,
|
| 1021 |
+
"step": 27000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.8,
|
| 1025 |
+
"eval_gen_len": 126.5218,
|
| 1026 |
+
"eval_loss": 1.5084278583526611,
|
| 1027 |
+
"eval_rouge1": 45.4964,
|
| 1028 |
+
"eval_rouge2": 21.4702,
|
| 1029 |
+
"eval_rougeL": 31.177,
|
| 1030 |
+
"eval_rougeLsum": 40.5432,
|
| 1031 |
+
"eval_runtime": 5530.5865,
|
| 1032 |
+
"eval_samples_per_second": 1.199,
|
| 1033 |
+
"eval_steps_per_second": 0.15,
|
| 1034 |
+
"step": 27000
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.83,
|
| 1038 |
+
"learning_rate": 1.942610010450715e-05,
|
| 1039 |
+
"loss": 0.8839,
|
| 1040 |
+
"step": 27500
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.83,
|
| 1044 |
+
"eval_gen_len": 126.8648,
|
| 1045 |
+
"eval_loss": 1.5090144872665405,
|
| 1046 |
+
"eval_rouge1": 45.6279,
|
| 1047 |
+
"eval_rouge2": 21.5346,
|
| 1048 |
+
"eval_rougeL": 31.252,
|
| 1049 |
+
"eval_rougeLsum": 40.6096,
|
| 1050 |
+
"eval_runtime": 5522.5033,
|
| 1051 |
+
"eval_samples_per_second": 1.201,
|
| 1052 |
+
"eval_steps_per_second": 0.15,
|
| 1053 |
+
"step": 27500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.87,
|
| 1057 |
+
"learning_rate": 1.8870211015498187e-05,
|
| 1058 |
+
"loss": 0.8899,
|
| 1059 |
+
"step": 28000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.87,
|
| 1063 |
+
"eval_gen_len": 126.8498,
|
| 1064 |
+
"eval_loss": 1.5073039531707764,
|
| 1065 |
+
"eval_rouge1": 45.6406,
|
| 1066 |
+
"eval_rouge2": 21.5551,
|
| 1067 |
+
"eval_rougeL": 31.2519,
|
| 1068 |
+
"eval_rougeLsum": 40.6425,
|
| 1069 |
+
"eval_runtime": 5520.5026,
|
| 1070 |
+
"eval_samples_per_second": 1.202,
|
| 1071 |
+
"eval_steps_per_second": 0.15,
|
| 1072 |
+
"step": 28000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.9,
|
| 1076 |
+
"learning_rate": 1.8314321926489228e-05,
|
| 1077 |
+
"loss": 0.8904,
|
| 1078 |
+
"step": 28500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.9,
|
| 1082 |
+
"eval_gen_len": 126.689,
|
| 1083 |
+
"eval_loss": 1.5086652040481567,
|
| 1084 |
+
"eval_rouge1": 45.7334,
|
| 1085 |
+
"eval_rouge2": 21.7071,
|
| 1086 |
+
"eval_rougeL": 31.3069,
|
| 1087 |
+
"eval_rougeLsum": 40.6992,
|
| 1088 |
+
"eval_runtime": 5519.0861,
|
| 1089 |
+
"eval_samples_per_second": 1.202,
|
| 1090 |
+
"eval_steps_per_second": 0.15,
|
| 1091 |
+
"step": 28500
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.93,
|
| 1095 |
+
"learning_rate": 1.7758432837480266e-05,
|
| 1096 |
+
"loss": 0.8958,
|
| 1097 |
+
"step": 29000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.93,
|
| 1101 |
+
"eval_gen_len": 126.9157,
|
| 1102 |
+
"eval_loss": 1.5112992525100708,
|
| 1103 |
+
"eval_rouge1": 45.4618,
|
| 1104 |
+
"eval_rouge2": 21.4623,
|
| 1105 |
+
"eval_rougeL": 31.0914,
|
| 1106 |
+
"eval_rougeLsum": 40.4648,
|
| 1107 |
+
"eval_runtime": 5520.0088,
|
| 1108 |
+
"eval_samples_per_second": 1.202,
|
| 1109 |
+
"eval_steps_per_second": 0.15,
|
| 1110 |
+
"step": 29000
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.97,
|
| 1114 |
+
"learning_rate": 1.7202543748471307e-05,
|
| 1115 |
+
"loss": 0.8991,
|
| 1116 |
+
"step": 29500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.97,
|
| 1120 |
+
"eval_gen_len": 126.7855,
|
| 1121 |
+
"eval_loss": 1.5126971006393433,
|
| 1122 |
+
"eval_rouge1": 45.6364,
|
| 1123 |
+
"eval_rouge2": 21.5467,
|
| 1124 |
+
"eval_rougeL": 31.2001,
|
| 1125 |
+
"eval_rougeLsum": 40.5946,
|
| 1126 |
+
"eval_runtime": 5532.4138,
|
| 1127 |
+
"eval_samples_per_second": 1.199,
|
| 1128 |
+
"eval_steps_per_second": 0.15,
|
| 1129 |
+
"step": 29500
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.0,
|
| 1133 |
+
"learning_rate": 1.6646654659462345e-05,
|
| 1134 |
+
"loss": 0.889,
|
| 1135 |
+
"step": 30000
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.0,
|
| 1139 |
+
"eval_gen_len": 126.6989,
|
| 1140 |
+
"eval_loss": 1.5128982067108154,
|
| 1141 |
+
"eval_rouge1": 45.3668,
|
| 1142 |
+
"eval_rouge2": 21.3563,
|
| 1143 |
+
"eval_rougeL": 30.998,
|
| 1144 |
+
"eval_rougeLsum": 40.3714,
|
| 1145 |
+
"eval_runtime": 5736.9272,
|
| 1146 |
+
"eval_samples_per_second": 1.156,
|
| 1147 |
+
"eval_steps_per_second": 0.145,
|
| 1148 |
+
"step": 30000
|
| 1149 |
+
}
|
| 1150 |
+
],
|
| 1151 |
+
"max_steps": 44973,
|
| 1152 |
+
"num_train_epochs": 3,
|
| 1153 |
+
"total_flos": 7.801293866564321e+17,
|
| 1154 |
+
"trial_name": null,
|
| 1155 |
+
"trial_params": null
|
| 1156 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71a6e55853e1185615590ece7402cc04f12cebc0d4953dbb1d2e764254b022d1
|
| 3 |
+
size 3055
|